Research agents

3,519 tagged Research, measured the same way as everything else here.

Browse within: claude-code-plugin 130academic-writing 120academic-research 89prompt-engineering 63literature-review 60ai-research 58ai-tools 56academic-pipeline 54ai-governance 47ai-coding 46agentic-workflow 44Multi-Agent 42ai-assistant 40skills 39

advisor-agent

193

Lirsakura/skills-hub

Agent

A research assistant for investigating graduate-school advisers. Given an adviser’s name and institution, it produces a report on publications, public reviews, and the lab environment using facts and sources.

not rated 10 6mo ago A 77 tokens

adapter-investigator

195

Ninjabeam20/SportIQ-MCP

Agent Claude Code

Probes a candidate data-source endpoint, captures sample responses, drafts an adapter module and wiki page. Use when evaluating a new source for a chain.

not rated 10 2d ago A 34 tokens original MIT

gods-generator

196

aitorllj93/babilim-info

Agent

You are a librarian expert in religion and mythology. Your goal is to manage a knowledge base with all the names of Gods of all cultures throughout humanity.

not rated 10 5mo ago A 0 tokens

Brainstorm

197

zhangyu94/humanfile

Agent

Brainstorm user-visible product features by reviewing this repository and researching related open-source projects, papers, and high-quality blogs/docs. Use when: feature ideation, roadmap exploration, innovation spikes, competitive analysis.

not rated 10 4mo ago A 44 tokens original MIT

benjaminshafii/digital-empire

Agent Claude Code

Use this agent when you need to research and document current best practices for local LLM implementation, structured outputs, prompt engineering, or performance optimization. Examples:\n\n \nContext: The team is implementing a new feature that requires multiple LLM calls and wants to optimize the approach.\nuser…

not rated 10 6mo ago A 0 tokens

bbinto/bb-chiefofstaff

Agent

Monitor multiple sources of product thought leadership and identify new topics, trends, and insights that the Product Director needs to know about. This agent surfaces emerging product management concepts, industry trends, and thought leadership that may impact product strategy. Use the…

not rated 10 13d ago A 0 tokens

competitor-researcher

200

giadaf-boosha/claude-code

Agent Claude Code

Mappa il panorama competitivo di {PRODOTTO/SERVIZIO} in qualsiasi settore e ne sintetizza posizionamento, gap e differenziatori. Primo step della catena marketing, prima del brief.

not rated 10 today A 49 tokens

web-search-agent

201

Islam-amara1/hormozi-workspace

Agent Claude Code

Use when researching information on the internet — debugging issues, technical problems, or gathering comprehensive information from multiple sources.

not rated 10 4mo ago A 26 tokens

matsuni-kk/agent_template_public

Agent Codex

A browser-based research agent that runs at least three searches or brainstorming tasks in parallel through a browser extension. It can use extended reasoning and, when requested, ChatGPT Pro for deeper analysis and fact-checking.

not rated 10 7mo ago A 110 tokens

eliranwong/biblemate-agentic-workspace

Agent Claude Code

Integrate all study outputs into a single, comprehensive, publication-quality final document. Write through iterative drafting, integrating, auditing, and revising — never in a single pass.

not rated 10 1mo ago A 42 tokens

explorer-rag-enhanced

204

HumanBean17/jrag

Agent

MUST BE USED PROACTIVELY. Universal read-only explorer agent. Combines jrag graph navigation (call chains, service boundaries, routes, impact analysis, FQN resolution) with broad file-system search (grep, glob, excerpt reading). Use for any exploration task: locating code, tracing dependencies, finding patterns…

not rated 9 3d ago A 93 tokens original MIT

academic-psychologist

205

hottweelz/writing-template-for-ai

Agent

Expert in human behavior, personality theory, motivation, and cognitive patterns — builds psychologically credible characters and interactions grounded in clinical and research frameworks.

not rated 9 2mo ago A 0 tokens original MIT

history-fact-checker

206

quzhi1/HistoryAgentSkills

Agent Claude Code

A review agent for answers about Chinese history that checks cited historical sources and the details included in the answer.

not rated 9 yesterday A 104 tokens

hep-orchestrator

207

huangzhonglv/hep-workflow

Agent Claude Code

Top-level orchestrator for the HEP phenomenology workflow. Coordinates project state, checks prerequisites, dispatches skills, and validates outputs. Trigger when the user says: "start a new project", "run the full pipeline", "continue my project", "project status", "project progress", "what's next", or any request to…

not rated 9 1mo ago A 109 tokens original MIT

search-engineer

208

ChangooLee/mcp-kr-legislation

Agent

A coding agent for improving search of laws and regulations. It works with BM25 keyword search, similar-text search, and hybrid search, which combines different search methods.

not rated 9 4mo ago A 0 tokens

white-hat-researcher

209

kaltinril/Kernsmith

Agent Claude Code

Elite white-hat security researcher. Exhaustive vulnerability hunter — from blank passwords to chained exploits. Finds everything that could embarrass a business before a real attacker does.

not rated 9 7d ago A 40 tokens original MIT

agent-anthropologist

210

pablodiegoo/Data-Pro-Skill

Agent

Qualitative research persona. Analyzes open-ended responses, interviews, focus groups. Categorizes themes, extracts verbatims, identifies latent needs, maps archetypes and journeys. Activated by /mode:quali and /inject-open.

not rated 8 1mo ago A 54 tokens original MIT

reviewer

211

whenpoem/aiscientist

Agent Claude Code

Adversarial reviewer of finished manuscripts. Refuses to sign off on central result claims until publication-critical metrics trace back to pinned evidence (empirical checklist) AND theorem claims trace back to an empty diagnostic manifest plus either a Lean verification or an explicit unverified flag (proof…

not rated 8 1mo ago A 59 tokens original MIT

MrBinnacle/azimuth

Agent Claude Code

Audits a proposed numeric heuristic, threshold, cap, or empirical claim destined for SKILL.md or a reference file against AZIMUTH's existing evidence base. Returns citation found, [uncalibrated] tag warranted, or contradicting evidence. Read-only — never modifies SKILL.md or references. Use before any new…

not rated 8 3mo ago A 78 tokens original MIT

fahrellgiovanny/nothing-new-under-the-sun

Agent

There Is Nothing New Under The Sun — a read-only scouting agent. Searches existing solutions (codebase, dependencies, packages, GitHub repos, APIs, SaaS, templates) before anyone writes code. Outputs a REUSE / USE / FORK / BUY / INTEGRATE / BUILD recommendation with a required schema and evidence matrix. Uses…

not rated 8 1mo ago C 134 tokens original MIT

TechWatching/copilot-goodies

Agent

Generate comprehensive retro specifications of live websites by browsing with Playwright MCP, capturing structure, content, functionality, and creating architectural documentation.

not rated 8 2mo ago A 32 tokens original MIT

report_validator

215

pppop00/Equity-Research-Company

Agent

A validator for generated HTML research reports. It checks the required template, validation results, report structure, charts, and selected data consistency.

not rated 8 +1 1mo ago A 0 tokens original Apache-2.0

artifact-analyzer

216

2233admin/design-pipeline

Agent Codex

You are a research analyst. Your job is to scan project documents and extract information relevant to a product concept being stress-tested through the PRFAQ process.

not rated 7 2d ago A 0 tokens copy · 100% MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: